Creating Tabletop RPG Dialogues via Retrieval-Augmented Generation
Authors:
- Gabriel Rudan Sales MatosGMGabriel Rudan Sales Matos
- José Wellington Franco da SilvaJSJosé Wellington Franco da Silva
- Artur de Oliveira da Rocha FrancoAFArtur de Oliveira da Rocha Franco
- José Gilvan Rodrigues MaiaJMJosé Gilvan Rodrigues Maia
- José Antônio Fernandes de MacêdoJMJosé Antônio Fernandes de Macêdo
Open Access
- 30 September 2025
- conference paper
- Published by Sociedade Brasileira de Computação
- p. 550-562
Abstract
Introduction: Tabletop RPGs (TRPGs) rely heavily on narrative, but Game Masters face challenges creating coherent and engaging dialogues while managing extensive rulebooks. Objective: This work investigates the adoption of Retrieval-Augmented Generation (RAG) to improve dialogue generation in TRPGs using Large Language Models. Methodology or Steps: Four dialogues were analyzed: two handwritten and two generated by LLMs—with and without RAG. Eleven participants rated them across five criteria—Engagement, Coherence, Cohesion, Creativity, and Surprise. Results: RAG-based generation outperformed standard LLMs across all categories, improving coherence (+0.18), cohesion (+0.46), creativity (+0.55), engagement (+0.91), and surprise (+0.64). Compared to handwritten dialogues, generated ones were rated higher in cohesion (3.91 vs. 3.68) and matched in coherence (3.82), although handwritten dialogues remained superior in engagement (3.82 vs. 3.09) and creativity (3.68 vs. 3.14).Keywords
This publication has 20 references indexed in Scilit:
- Managing and controlling digital role-playing game elements: A current state of affairsEntertainment Computing, 2024
- LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT2024
- Analyzing Embedding Models for Embedding Vectors in Vector Databases2023
- Comparison of GPT-3.5, GPT-4, and human user performance on a practice ophthalmology written examinationEye, 2023
- ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scopeInternet of Things and Cyber-Physical Systems, 2023
- Google Colaboratory2019
- Quality Control in CrowdsourcingACM Computing Surveys, 2018
- Dialogue and interaction in role-playing games2017
- Narrative Structure and Player Experience in Role-Playing GamesInternational Journal of Human–Computer Interaction, 2014
- What can crowdsourcing do for decision support?Decision Support Systems, 2014